Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of experimental groups and conditions in research contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -1.00
    RectangleBorder
    -0.89
     propOrder
    -0.88
     oprot
    -0.81
     فريبيس
    -0.78
     дописавши
    -0.78
     WaitForSeconds
    -0.77
     виправивши
    -0.77
    +#+#
    -0.75
     tartalomajánló
    -0.75
    POSITIVE LOGITS
     shallow
    0.51
    shallow
    0.50
     Shallow
    0.48
     חיצוניים
    0.46
     conventional
    0.44
    ้าม
    0.44
    काल
    0.43
    ocus
    0.43
    uko
    0.43
    cold
    0.43
    Act Density 0.015%

    No Known Activations